Pub Date : 2024-08-29DOI: 10.1016/S2589-7500(24)00193-6
Virimchi Pillutla , Adam B Landman , Jagmeet P Singh
{"title":"Digital technology and new care pathways will redefine the cardiovascular workforce","authors":"Virimchi Pillutla , Adam B Landman , Jagmeet P Singh","doi":"10.1016/S2589-7500(24)00193-6","DOIUrl":"10.1016/S2589-7500(24)00193-6","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 10","pages":"Pages e674-e676"},"PeriodicalIF":23.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1016/S2589-7500(24)00194-8
The Lancet Digital Health
{"title":"Promises and challenges of digital tools in cardiovascular care","authors":"The Lancet Digital Health","doi":"10.1016/S2589-7500(24)00194-8","DOIUrl":"10.1016/S2589-7500(24)00194-8","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 10","pages":"Page e673"},"PeriodicalIF":23.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1016/S2589-7500(24)00158-4
Prof Peder L Myhre MD PhD , Jasper Tromp MD PhD , Wouter Ouwerkerk MD PhD , Daniel S W Ting MD PhD , Kieran F Docherty MD PhD , Prof C Michael Gibson MS MD , Prof Carolyn S P Lam MD PhD
This Series paper provides an overview of digital tools in heart failure care, encompassing screening, early diagnosis, treatment initiation and optimisation, and monitoring, and the implications these tools could have for research. The current medical environment favours the implementation of digital tools in heart failure due to rapid advancements in technology and computing power, unprecedented global connectivity, and the paradigm shift towards digitisation. Despite available effective therapies for heart failure, substantial inadequacies in managing the condition have hindered improvements in patient outcomes, particularly in low-income and middle-income countries. As digital health tools continue to evolve and exert a growing influence on both clinical care and research, establishing clinical frameworks and supportive ecosystems that enable their effective use on a global scale is crucial.
{"title":"Digital tools in heart failure: addressing unmet needs","authors":"Prof Peder L Myhre MD PhD , Jasper Tromp MD PhD , Wouter Ouwerkerk MD PhD , Daniel S W Ting MD PhD , Kieran F Docherty MD PhD , Prof C Michael Gibson MS MD , Prof Carolyn S P Lam MD PhD","doi":"10.1016/S2589-7500(24)00158-4","DOIUrl":"10.1016/S2589-7500(24)00158-4","url":null,"abstract":"<div><div>This Series paper provides an overview of digital tools in heart failure care, encompassing screening, early diagnosis, treatment initiation and optimisation, and monitoring, and the implications these tools could have for research. The current medical environment favours the implementation of digital tools in heart failure due to rapid advancements in technology and computing power, unprecedented global connectivity, and the paradigm shift towards digitisation. Despite available effective therapies for heart failure, substantial inadequacies in managing the condition have hindered improvements in patient outcomes, particularly in low-income and middle-income countries. As digital health tools continue to evolve and exert a growing influence on both clinical care and research, establishing clinical frameworks and supportive ecosystems that enable their effective use on a global scale is crucial.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 10","pages":"Pages e755-e766"},"PeriodicalIF":23.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1016/S2589-7500(24)00142-0
Prof Partho P Sengupta MD , Prof Damini Dey PhD , Rhodri H Davies PhD , Nicolas Duchateau PhD , Naveena Yanamala PhD
Artificial Intelligence (AI), through deep learning, has brought automation and predictive capabilities to cardiac imaging. However, despite considerable investment, tangible health-care cost reductions remain unproven. Although AI holds promise, there has been insufficient time for both methodological development and prospective clinical trials to establish its advantage over human interpretations in terms of its effect on patient outcomes. Challenges such as data scarcity, privacy issues, and ethical concerns impede optimal AI training. Furthermore, the absence of a unified model for the complex structure and function of the heart and evolving domain knowledge can introduce heuristic biases and influence underlying assumptions in model development. Integrating AI into diverse institutional picture archiving and communication systems and devices also presents a clinical hurdle. This hurdle is further compounded by an absence of high-quality labelled data, difficulty sharing data between institutions, and non-uniform and inadequate gold standards for external validations and comparisons of model performance in real-world settings. Nevertheless, there is a strong push in industry and academia for AI solutions in medical imaging. This Series paper reviews key studies and identifies challenges that require a pragmatic change in the approach for using AI for cardiac imaging, whereby AI is viewed as augmented intelligence to complement, not replace, human judgement. The focus should shift from isolated measurements to integrating non-linear and complex data towards identifying disease phenotypes—emphasising pattern recognition where AI excels. Algorithms should enhance imaging reports, enriching patients' understanding, communication between patients and clinicians, and shared decision making. The emergence of professional standards and guidelines is essential to address these developments and ensure the safe and effective integration of AI in cardiac imaging.
{"title":"Challenges for augmenting intelligence in cardiac imaging","authors":"Prof Partho P Sengupta MD , Prof Damini Dey PhD , Rhodri H Davies PhD , Nicolas Duchateau PhD , Naveena Yanamala PhD","doi":"10.1016/S2589-7500(24)00142-0","DOIUrl":"10.1016/S2589-7500(24)00142-0","url":null,"abstract":"<div><div>Artificial Intelligence (AI), through deep learning, has brought automation and predictive capabilities to cardiac imaging. However, despite considerable investment, tangible health-care cost reductions remain unproven. Although AI holds promise, there has been insufficient time for both methodological development and prospective clinical trials to establish its advantage over human interpretations in terms of its effect on patient outcomes. Challenges such as data scarcity, privacy issues, and ethical concerns impede optimal AI training. Furthermore, the absence of a unified model for the complex structure and function of the heart and evolving domain knowledge can introduce heuristic biases and influence underlying assumptions in model development. Integrating AI into diverse institutional picture archiving and communication systems and devices also presents a clinical hurdle. This hurdle is further compounded by an absence of high-quality labelled data, difficulty sharing data between institutions, and non-uniform and inadequate gold standards for external validations and comparisons of model performance in real-world settings. Nevertheless, there is a strong push in industry and academia for AI solutions in medical imaging. This Series paper reviews key studies and identifies challenges that require a pragmatic change in the approach for using AI for cardiac imaging, whereby AI is viewed as augmented intelligence to complement, not replace, human judgement. The focus should shift from isolated measurements to integrating non-linear and complex data towards identifying disease phenotypes—emphasising pattern recognition where AI excels. Algorithms should enhance imaging reports, enriching patients' understanding, communication between patients and clinicians, and shared decision making. The emergence of professional standards and guidelines is essential to address these developments and ensure the safe and effective integration of AI in cardiac imaging.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 10","pages":"Pages e739-e748"},"PeriodicalIF":23.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1016/S2589-7500(24)00191-2
Betül Toprak MD , Hugo Solleder PhD , Eleonora Di Carluccio MSc , Jaimi H Greenslade PhD , Prof William A Parsonage MD , Karen Schulz DC , Prof Louise Cullen MD , Prof Fred S Apple PhD , Prof Andreas Ziegler PhD , Prof Stefan Blankenberg MD
<div><h3>Background</h3><div>Point-of-care (POC) high-sensitivity cardiac troponin (hs-cTn) assays have been shown to provide similar analytical precision despite substantially shorter turnaround times compared with laboratory-based hs-cTn assays. We applied the previously developed machine learning based personalised Artificial Intelligence in Suspected Myocardial Infarction Study (ARTEMIS) algorithm, which can predict the individual probability of myocardial infarction, with a single POC hs-cTn measurement, and compared its diagnostic performance with standard-of-care pathways for rapid rule-out of myocardial infarction.</div></div><div><h3>Methods</h3><div>We retrospectively analysed pooled data from consecutive patients of two prospective observational cohorts in geographically distinct regions (the Safe Emergency Department Discharge Rate cohort from the USA and the Suspected Acute Myocardial Infarction in Emergency cohort from Australia) who presented to the emergency department with suspected myocardial infarction. Patients with ST-segment elevation myocardial infarction were excluded. Safety and efficacy of direct rule-out of myocardial infarction by the ARTEMIS algorithm (at a pre-specified probability threshold of <0·5%) were compared with the European Society of Cardiology (ESC)-recommended and the American College of Cardiology (ACC)-recommended 0 h pathways using a single POC high-sensitivity cardiac troponin I (hs-cTnI) measurement (Siemens Atellica VTLi as investigational assay). The primary diagnostic outcome was an adjudicated index diagnosis of type 1 or type 2 myocardial infarction according to the Fourth Universal Definition of Myocardial Infarction. The safety outcome was a composite of incident myocardial infarction and cardiovascular death (follow-up events) at 30 days. Additional analyses were performed for type I myocardial infarction only (secondary diagnostic outcome), and for each cohort separately. Subgroup analyses were performed for age (<65 years <em>vs</em> ≥65 years), sex, symptom onset (≤3 h <em>vs</em> >3 h), estimated glomerular filtration rate (<60 mL/min per 1·73 m<sup>2</sup> <em>vs</em> ≥60 mL/min per 1·73 m<sup>2</sup>), and absence or presence of arterial hypertension, diabetes, a history of coronary artery disease, myocardial infarction, or heart failure, smoking, and ischaemic electrocardiogram signs.</div></div><div><h3>Findings</h3><div>Among 2560 patients (1075 [42%] women, median age 58 years [IQR 48·0–69·0]), prevalence of myocardial infarction was 6·5% (166/2560). The ARTEMIS-POC algorithm classified 899 patients (35·1%) as suitable for rapid rule-out with a negative predictive value of 99·96% (95% CI 99·64–99·96) and a sensitivity of 99·68% (97·21–99·70). For type I myocardial infarction only, negative predictive value and sensitivity were both 100%. Proportions of missed index myocardial infarction (0·05% [0·04–0·42]) and follow-up events at 30 days (0·07% [95% CI 0·06–0·59]) were l
{"title":"Diagnostic accuracy of a machine learning algorithm using point-of-care high-sensitivity cardiac troponin I for rapid rule-out of myocardial infarction: a retrospective study","authors":"Betül Toprak MD , Hugo Solleder PhD , Eleonora Di Carluccio MSc , Jaimi H Greenslade PhD , Prof William A Parsonage MD , Karen Schulz DC , Prof Louise Cullen MD , Prof Fred S Apple PhD , Prof Andreas Ziegler PhD , Prof Stefan Blankenberg MD","doi":"10.1016/S2589-7500(24)00191-2","DOIUrl":"10.1016/S2589-7500(24)00191-2","url":null,"abstract":"<div><h3>Background</h3><div>Point-of-care (POC) high-sensitivity cardiac troponin (hs-cTn) assays have been shown to provide similar analytical precision despite substantially shorter turnaround times compared with laboratory-based hs-cTn assays. We applied the previously developed machine learning based personalised Artificial Intelligence in Suspected Myocardial Infarction Study (ARTEMIS) algorithm, which can predict the individual probability of myocardial infarction, with a single POC hs-cTn measurement, and compared its diagnostic performance with standard-of-care pathways for rapid rule-out of myocardial infarction.</div></div><div><h3>Methods</h3><div>We retrospectively analysed pooled data from consecutive patients of two prospective observational cohorts in geographically distinct regions (the Safe Emergency Department Discharge Rate cohort from the USA and the Suspected Acute Myocardial Infarction in Emergency cohort from Australia) who presented to the emergency department with suspected myocardial infarction. Patients with ST-segment elevation myocardial infarction were excluded. Safety and efficacy of direct rule-out of myocardial infarction by the ARTEMIS algorithm (at a pre-specified probability threshold of <0·5%) were compared with the European Society of Cardiology (ESC)-recommended and the American College of Cardiology (ACC)-recommended 0 h pathways using a single POC high-sensitivity cardiac troponin I (hs-cTnI) measurement (Siemens Atellica VTLi as investigational assay). The primary diagnostic outcome was an adjudicated index diagnosis of type 1 or type 2 myocardial infarction according to the Fourth Universal Definition of Myocardial Infarction. The safety outcome was a composite of incident myocardial infarction and cardiovascular death (follow-up events) at 30 days. Additional analyses were performed for type I myocardial infarction only (secondary diagnostic outcome), and for each cohort separately. Subgroup analyses were performed for age (<65 years <em>vs</em> ≥65 years), sex, symptom onset (≤3 h <em>vs</em> >3 h), estimated glomerular filtration rate (<60 mL/min per 1·73 m<sup>2</sup> <em>vs</em> ≥60 mL/min per 1·73 m<sup>2</sup>), and absence or presence of arterial hypertension, diabetes, a history of coronary artery disease, myocardial infarction, or heart failure, smoking, and ischaemic electrocardiogram signs.</div></div><div><h3>Findings</h3><div>Among 2560 patients (1075 [42%] women, median age 58 years [IQR 48·0–69·0]), prevalence of myocardial infarction was 6·5% (166/2560). The ARTEMIS-POC algorithm classified 899 patients (35·1%) as suitable for rapid rule-out with a negative predictive value of 99·96% (95% CI 99·64–99·96) and a sensitivity of 99·68% (97·21–99·70). For type I myocardial infarction only, negative predictive value and sensitivity were both 100%. Proportions of missed index myocardial infarction (0·05% [0·04–0·42]) and follow-up events at 30 days (0·07% [95% CI 0·06–0·59]) were l","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 10","pages":"Pages e729-e738"},"PeriodicalIF":23.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-29DOI: 10.1016/S2589-7500(24)00151-1
Giorgio Quer PhD , Prof Eric J Topol MD
Cardiovascular diseases persist as the leading cause of death globally and their early detection and prediction remain a major challenge. Artificial intelligence (AI) tools can help meet this challenge as they have considerable potential for early diagnosis and prediction of occurrence of these diseases. Deep neural networks can improve the accuracy of medical image interpretation and their outputs can provide rich information that otherwise would not be detected by cardiologists. With recent advances in transformer models, multimodal AI, and large language models, the ability to integrate electronic health record data with images, genomics, biosensors, and other data has the potential to improve diagnosis and partition patients who are at high risk for primary preventive strategies. Although much emphasis has been placed on AI supporting clinicians, AI can also serve patients and provide immediate help with diagnosis, such as that of arrhythmia, and is being studied for automated self-imaging. Potential risks, such as loss of data privacy or potential diagnostic errors, should be addressed before use in clinical practice. This Series paper explores opportunities and limitations of AI models for cardiovascular medicine, and aims to identify specific barriers to and solutions in the application of AI models, facilitating their integration into health-care systems.
{"title":"The potential for large language models to transform cardiovascular medicine","authors":"Giorgio Quer PhD , Prof Eric J Topol MD","doi":"10.1016/S2589-7500(24)00151-1","DOIUrl":"10.1016/S2589-7500(24)00151-1","url":null,"abstract":"<div><div>Cardiovascular diseases persist as the leading cause of death globally and their early detection and prediction remain a major challenge. Artificial intelligence (AI) tools can help meet this challenge as they have considerable potential for early diagnosis and prediction of occurrence of these diseases. Deep neural networks can improve the accuracy of medical image interpretation and their outputs can provide rich information that otherwise would not be detected by cardiologists. With recent advances in transformer models, multimodal AI, and large language models, the ability to integrate electronic health record data with images, genomics, biosensors, and other data has the potential to improve diagnosis and partition patients who are at high risk for primary preventive strategies. Although much emphasis has been placed on AI supporting clinicians, AI can also serve patients and provide immediate help with diagnosis, such as that of arrhythmia, and is being studied for automated self-imaging. Potential risks, such as loss of data privacy or potential diagnostic errors, should be addressed before use in clinical practice. This Series paper explores opportunities and limitations of AI models for cardiovascular medicine, and aims to identify specific barriers to and solutions in the application of AI models, facilitating their integration into health-care systems.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 10","pages":"Pages e767-e771"},"PeriodicalIF":23.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Digital health technologies can generate data that can be used to train artificial intelligence (AI) algorithms, which have been particularly transformative in cardiovascular health-care delivery. However, digital and health-care data repositories that are used to train AI algorithms can introduce bias when data are homogeneous and health-care processes are inequitable. AI bias can also be introduced during algorithm development, testing, implementation, and post-implementation processes. The consequences of AI algorithmic bias can be considerable, including missed diagnoses, misclassification of disease, incorrect risk prediction, and inappropriate treatment recommendations. This bias can disproportionately affect marginalised demographic groups. In this Series paper, we provide a brief overview of AI applications in cardiovascular health care, discuss stages of algorithm development and associated sources of bias, and provide examples of harm from biased algorithms. We propose strategies that can be applied during the training, testing, and implementation of AI algorithms to mitigate bias so that all those at risk for or living with cardiovascular disease might benefit equally from AI.
{"title":"Mitigating the risk of artificial intelligence bias in cardiovascular care","authors":"Ariana Mihan MPH , Ambarish Pandey MD , Harriette GC Van Spall MD","doi":"10.1016/S2589-7500(24)00155-9","DOIUrl":"10.1016/S2589-7500(24)00155-9","url":null,"abstract":"<div><div>Digital health technologies can generate data that can be used to train artificial intelligence (AI) algorithms, which have been particularly transformative in cardiovascular health-care delivery. However, digital and health-care data repositories that are used to train AI algorithms can introduce bias when data are homogeneous and health-care processes are inequitable. AI bias can also be introduced during algorithm development, testing, implementation, and post-implementation processes. The consequences of AI algorithmic bias can be considerable, including missed diagnoses, misclassification of disease, incorrect risk prediction, and inappropriate treatment recommendations. This bias can disproportionately affect marginalised demographic groups. In this Series paper, we provide a brief overview of AI applications in cardiovascular health care, discuss stages of algorithm development and associated sources of bias, and provide examples of harm from biased algorithms. We propose strategies that can be applied during the training, testing, and implementation of AI algorithms to mitigate bias so that all those at risk for or living with cardiovascular disease might benefit equally from AI.</div></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 10","pages":"Pages e749-e754"},"PeriodicalIF":23.8,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142113573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-21DOI: 10.1016/S2589-7500(24)00123-7
Xiaoshuang Feng PhD , Patrick Goodley MBBCh , Karine Alcala MS , Florence Guida PhD , Prof Rudolf Kaaks PhD , Prof Roel Vermeulen PhD , George S Downward PhD , Catalina Bonet MSc , Sandra M Colorado-Yohar PhD , Demetrius Albanes MD , Stephanie J Weinstein PhD , Prof Marcel Goldberg PhD , Prof Marie Zins PhD , Prof Caroline Relton PhD , Prof Arnulf Langhammer PhD , Anne Heidi Skogholt PhD , Mattias Johansson PhD , Hilary A Robbins PhD
<div><h3>Background</h3><p>Lung cancer risk prediction models might efficiently identify individuals who should be offered lung cancer screening. However, their performance has not been comprehensively evaluated in Europe. We aimed to externally validate and evaluate the performance of several risk prediction models that predict lung cancer incidence or mortality in prospective European cohorts.</p></div><div><h3>Methods</h3><p>We analysed 240 137 participants aged 45–80 years with a current or former smoking history from nine European countries in four prospective cohorts from the pooled database of the Lung Cancer Cohort Consortium: the Alpha-Tocopherol, Beta-Carotene Cancer Prevention Study (Finland), the Nord-Trøndelag Health Study (Norway), CONSTANCES (France), and the European Prospective Investigation into Cancer and Nutrition (Denmark, Germany, Italy, Spain, Sweden, the Netherlands, and Norway). We evaluated ten lung cancer risk models, which comprised the Bach, the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial 2012 model (PLCO<sub>m2012</sub>), the Lung Cancer Risk Assessment Tool (LCRAT), the Lung Cancer Death Risk Assessment Tool (LCDRAT), the Nord-Trøndelag Health Study (HUNT), the Optimized Early Warning Model for Lung Cancer Risk (OWL), the University College London—Death (UCLD), the University College London—Incidence (UCLI), the Liverpool Lung Project version 2 (LLP version 2), and the Liverpool Lung Project version 3 (LLP version 3) models. We quantified model calibration as the ratio of expected to observed cases or deaths and discrimination using the area under the receiver operating characteristic curve (AUC). For each model, we also identified risk thresholds that would screen the same number of individuals as each of the US Preventive Services Task Force 2021 (USPSTF-2021), the US Preventive Services Task Force 2013 (USPSTF-2013), and the Nederlands–Leuvens Longkanker Screenings Onderzoek (NELSON) criteria.</p></div><div><h3>Findings</h3><p>Among the participants, 1734 lung cancer cases and 1072 lung cancer deaths occurred within five years of enrolment. Most models had reasonable calibration in most countries, although the LLP version 2 overpredicted risk by more than 50% in eight countries (expected to observed ≥1·50). The PLCO<sub>m2012</sub>, LCDRAT, LCRAT, Bach, HUNT, OWL, UCLD, and UCLI models showed similar discrimination in most countries, with AUCs ranging from 0·68 (95% CI 0·59–0·77) to 0·83 (0·78–0·89), whereas the LLP version 2 and LLP version 3 showed lower discrimination, with AUCs ranging from 0·64 (95% CI 0·57–0·72) to 0·78 (0·74–0·83). When pooling data from all countries (but excluding the HUNT cohort), 33·9% (73 313 of 216 387) of individuals were eligible by USPSTF-2021 criteria, which included 74·8% (1185) of lung cancers and 76·3% (730) of lung cancer deaths occurring over 5 years. Fewer individuals were selected by USPSTF-2013 and NELSON criteria. After applying thresholds to select a
{"title":"Evaluation of risk prediction models to select lung cancer screening participants in Europe: a prospective cohort consortium analysis","authors":"Xiaoshuang Feng PhD , Patrick Goodley MBBCh , Karine Alcala MS , Florence Guida PhD , Prof Rudolf Kaaks PhD , Prof Roel Vermeulen PhD , George S Downward PhD , Catalina Bonet MSc , Sandra M Colorado-Yohar PhD , Demetrius Albanes MD , Stephanie J Weinstein PhD , Prof Marcel Goldberg PhD , Prof Marie Zins PhD , Prof Caroline Relton PhD , Prof Arnulf Langhammer PhD , Anne Heidi Skogholt PhD , Mattias Johansson PhD , Hilary A Robbins PhD","doi":"10.1016/S2589-7500(24)00123-7","DOIUrl":"10.1016/S2589-7500(24)00123-7","url":null,"abstract":"<div><h3>Background</h3><p>Lung cancer risk prediction models might efficiently identify individuals who should be offered lung cancer screening. However, their performance has not been comprehensively evaluated in Europe. We aimed to externally validate and evaluate the performance of several risk prediction models that predict lung cancer incidence or mortality in prospective European cohorts.</p></div><div><h3>Methods</h3><p>We analysed 240 137 participants aged 45–80 years with a current or former smoking history from nine European countries in four prospective cohorts from the pooled database of the Lung Cancer Cohort Consortium: the Alpha-Tocopherol, Beta-Carotene Cancer Prevention Study (Finland), the Nord-Trøndelag Health Study (Norway), CONSTANCES (France), and the European Prospective Investigation into Cancer and Nutrition (Denmark, Germany, Italy, Spain, Sweden, the Netherlands, and Norway). We evaluated ten lung cancer risk models, which comprised the Bach, the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial 2012 model (PLCO<sub>m2012</sub>), the Lung Cancer Risk Assessment Tool (LCRAT), the Lung Cancer Death Risk Assessment Tool (LCDRAT), the Nord-Trøndelag Health Study (HUNT), the Optimized Early Warning Model for Lung Cancer Risk (OWL), the University College London—Death (UCLD), the University College London—Incidence (UCLI), the Liverpool Lung Project version 2 (LLP version 2), and the Liverpool Lung Project version 3 (LLP version 3) models. We quantified model calibration as the ratio of expected to observed cases or deaths and discrimination using the area under the receiver operating characteristic curve (AUC). For each model, we also identified risk thresholds that would screen the same number of individuals as each of the US Preventive Services Task Force 2021 (USPSTF-2021), the US Preventive Services Task Force 2013 (USPSTF-2013), and the Nederlands–Leuvens Longkanker Screenings Onderzoek (NELSON) criteria.</p></div><div><h3>Findings</h3><p>Among the participants, 1734 lung cancer cases and 1072 lung cancer deaths occurred within five years of enrolment. Most models had reasonable calibration in most countries, although the LLP version 2 overpredicted risk by more than 50% in eight countries (expected to observed ≥1·50). The PLCO<sub>m2012</sub>, LCDRAT, LCRAT, Bach, HUNT, OWL, UCLD, and UCLI models showed similar discrimination in most countries, with AUCs ranging from 0·68 (95% CI 0·59–0·77) to 0·83 (0·78–0·89), whereas the LLP version 2 and LLP version 3 showed lower discrimination, with AUCs ranging from 0·64 (95% CI 0·57–0·72) to 0·78 (0·74–0·83). When pooling data from all countries (but excluding the HUNT cohort), 33·9% (73 313 of 216 387) of individuals were eligible by USPSTF-2021 criteria, which included 74·8% (1185) of lung cancers and 76·3% (730) of lung cancer deaths occurring over 5 years. Fewer individuals were selected by USPSTF-2013 and NELSON criteria. After applying thresholds to select a ","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Pages e614-e624"},"PeriodicalIF":23.8,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001237/pdfft?md5=f39b6b82aa1c03f5fab734e0e84a6e1f&pid=1-s2.0-S2589750024001237-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-21DOI: 10.1016/S2589-7500(24)00124-9
Oscar Freyer , Isabella Catharina Wiest Dr med , Prof Jakob Nikolas Kather Dr med , Stephen Gilbert PhD
Among the rapid integration of artificial intelligence in clinical settings, large language models (LLMs), such as Generative Pre-trained Transformer-4, have emerged as multifaceted tools that have potential for health-care delivery, diagnosis, and patient care. However, deployment of LLMs raises substantial regulatory and safety concerns. Due to their high output variability, poor inherent explainability, and the risk of so-called AI hallucinations, LLM-based health-care applications that serve a medical purpose face regulatory challenges for approval as medical devices under US and EU laws, including the recently passed EU Artificial Intelligence Act. Despite unaddressed risks for patients, including misdiagnosis and unverified medical advice, such applications are available on the market. The regulatory ambiguity surrounding these tools creates an urgent need for frameworks that accommodate their unique capabilities and limitations. Alongside the development of these frameworks, existing regulations should be enforced. If regulators fear enforcing the regulations in a market dominated by supply or development by large technology companies, the consequences of layperson harm will force belated action, damaging the potentiality of LLM-based applications for layperson medical advice.
{"title":"A future role for health applications of large language models depends on regulators enforcing safety standards","authors":"Oscar Freyer , Isabella Catharina Wiest Dr med , Prof Jakob Nikolas Kather Dr med , Stephen Gilbert PhD","doi":"10.1016/S2589-7500(24)00124-9","DOIUrl":"10.1016/S2589-7500(24)00124-9","url":null,"abstract":"<div><p>Among the rapid integration of artificial intelligence in clinical settings, large language models (LLMs), such as Generative Pre-trained Transformer-4, have emerged as multifaceted tools that have potential for health-care delivery, diagnosis, and patient care. However, deployment of LLMs raises substantial regulatory and safety concerns. Due to their high output variability, poor inherent explainability, and the risk of so-called AI hallucinations, LLM-based health-care applications that serve a medical purpose face regulatory challenges for approval as medical devices under US and EU laws, including the recently passed EU Artificial Intelligence Act. Despite unaddressed risks for patients, including misdiagnosis and unverified medical advice, such applications are available on the market. The regulatory ambiguity surrounding these tools creates an urgent need for frameworks that accommodate their unique capabilities and limitations. Alongside the development of these frameworks, existing regulations should be enforced. If regulators fear enforcing the regulations in a market dominated by supply or development by large technology companies, the consequences of layperson harm will force belated action, damaging the potentiality of LLM-based applications for layperson medical advice.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Pages e662-e672"},"PeriodicalIF":23.8,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001249/pdfft?md5=2df13b013a0e89af3fe332b6bcb83ed0&pid=1-s2.0-S2589750024001249-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-21DOI: 10.1016/S2589-7500(24)00175-4
The Lancet Digital Health
{"title":"Balancing AI innovation with patient safety","authors":"The Lancet Digital Health","doi":"10.1016/S2589-7500(24)00175-4","DOIUrl":"10.1016/S2589-7500(24)00175-4","url":null,"abstract":"","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 9","pages":"Page e601"},"PeriodicalIF":23.8,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024001754/pdfft?md5=0a8eaf69e78527e6cec35e921968cd32&pid=1-s2.0-S2589750024001754-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142041039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}